@InProceedings{Cech-IWCIA-2008, IS = { zkontrolovano 30 Dec 2008 }, UPDATE = { 2008-05-13 }, author = {{\v C}ech, Jan and {\v S}{\'a}ra, Radim}, title = {Windowpane Detection based on Maximum Aposteriori Probability Labeling}, booktitle = {Image Analysis - From Theory to Applications, Proceedings of the 12th International Workshop on Combinatorial Image Analysis (IWCIA'08)}, ISBN = {978-3-540-78274-2}, pages = {3-11}, book_pages = {243}, year = {2008}, month = {April}, day = {9}, venue = {Buffalo, USA}, annote = {Segmentation of windowpanes in images of building facades is formulated as a task of maximum aposteriori probability labeling. Assuming orthographic rectification of the image, the windowpanes are always axis-parallel rectangles of relatively low variability in appearance. Every image pixel has one of 10 possible labels, and the labels in adjacent pixels are constrained by allowed label configuration, such that the image labels represent a set of non-overlapping rectangles. The task of finding the most probable labeling of a given image leads to NP-hard discrete optimization problem. However, we find an approximate solution using a general solver suitable for such problems and we obtain promising results which we demonstrate on several experiments. Substantial difference between the presented paper and the state-of-the-art papers on segmentation based on Markov Random Fields is that we have a strong structure model, forcing the labels to form rectangles, while other methods do not model the structure at all, they typically only have a penalty when adjacent labels are different, in order to make resulting patches more continuous to reduce influence of noise and prevent over-segmentation. The difference is assessed experimentally.}, keywords = {constrained segmentation, Markov Random Field, probabilistic labeling, structure model}, publisher = {Research Publishing Services}, address = {Singapore, Singapore}, editor = {Barneva, Reneta P. and Brimkov, Vladimir}, project = {1ET101210407, FP6-IST-027113}, authorship = {50-50}, }